tailieunhanh - Báo cáo khoa học: "Towards Style Transformation from Written-Style to Audio-Style"

In this paper, we address the problem of optimizing the style of textual content to make it more suitable to being listened to by a user as opposed to being read. We study the differences between the written style and the audio style by consulting the linguistics and journalism literatures. Guided by this study, we suggest a number of linguistic features to distinguish between the two styles. | Towards Style Transformation from Written-Style to Audio-Style Amjad Abu-Jbara EECS Department University of Michigan Ann Arbor MI USA amjbara@ Barbara Rosario Intel Labs Santa Clara CA USA Kent Lyons Intel Labs Santa Clara CA USA Abstract In this paper we address the problem of optimizing the style of textual content to make it more suitable to being listened to by a user as opposed to being read. We study the differences between the written style and the audio style by consulting the linguistics and journalism literatures. Guided by this study we suggest a number of linguistic features to distinguish between the two styles. We show the correctness of our features and the impact of style transformation on the user experience through statistical analysis a style classification task and a user study. 1 Introduction We live in a world with an ever increasing amount and variety of information. A great deal of that content is in a textual format. Mobile technologies have increased our expectations as to when where and how we can access such content. As such it is not uncommon to want to gain access to this information when a visual display is not convenient or available while driving or walking for example . One way of addressing this issue is to use audio displays and in particular have users listen to content read to them by a speech synthesizer instead of reading it themselves on a display. While listening to speech opens many opportunities it also has issues which must be considered when using it as a replacement for reading. One important consideration is that the text that was originally written to be read might not be suitable to be listened to. Journalists for example write differently for audio . radio news broadcast compared Work conducted while interning at Intel Labs 248 to writing content meant to be read . newspaper articles Fang 1991 . One key reason for the difference is that understanding is